from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Sinh:] [:Cf:]]')
# TODO: ᵑɡ or ⁿɡ ?
# TODO: No t͡ʃ d͡ʒ ?
# TODO: No əː ?
PHONEMES = makePhonemeSet("""
m n ɲ ŋ
p b ᵐb ⁿd d t ʈ ɖ ⁿɖ k ɡ ⁿɡ
s ʃ
c ɟ
f h
r
l j
w
i iː u uː
e eː ə əː o oː
æː æ a aː
ei̯ ou̯ ou̯
æi̯ ai̯ au̯
.
""")
check('si-si_FONIPA.txt', GRAPHEMES, PHONEMES)
regtest('si-si_FONIPA', GRAPHEMES, PHONEMES)
PHONEMES = makePhonemeSet("""
m̥ m n̥ n ɲ̥ ɲ ŋ̊ ŋ ɴ
p pʰ b t tʰ d t͡ɕ t͡ɕʰ d͡ʑ k kʰ g ʔ
θ s sʰ z ʃ h
w̥ w j
l̥ l
í ì ḭ
ú ù ṵ
ʊ ʊ́ ʊ̀ ʊ̰
ɪ ɪ́ ɪ̀ ɪ̰
e é è ḛ
ó ò o̰
ə
ɛ ɛ́ ɛ̀ ɛ̰
ɔ́ ɔ̀ ɔ̰
æ
a á à a̰
eɪ̯ éɪ̯ èɪ̯ ḛɪ̯
oʊ̯ óʊ̯ òʊ̯ o̰ʊ̯
əʊ̯
aɪ̯ áɪ̯ àɪ̯ a̰ɪ̯
aʊ̯ áʊ̯ àʊ̯ a̰ʊ̯
.
""")
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import icu
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Latn:]]')
PHONEMES = makePhonemeSet("""
m n ŋ
p b t d k ɡ
f v s z ʃ ʒ h
t͡s d͡ʒ
ɾ l j w
i u
e o
a
ei̯ eu̯ oi̯
ai̯ au̯
.
""")
check('ia-ia_FONIPA.txt', GRAPHEMES, PHONEMES)
regtest('ia-ia_FONIPA', GRAPHEMES, PHONEMES)
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import codecs
import icu
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Sinh:] [:Cf:]]')
PHONEMES = makePhonemeSet("""
p b t d c ɟ ʈ ɖ k g
m n ɲ ŋ b̃ d̃ ɖ̃ ɟ̃ g̃ f s ʃ h
r l j ʋ ɑ ɑː æ æː i iː
u uː e eː o oː ə əː ɑ̃ː æ̃ː ə̃ː
ɑ̯i ɑu iu ei eu æi æu ɑi̯ ɑ̯u oi ou ui ɑːi
eːi oːi oːu uːi æːi ɑːu æːu iːu w
.
""")
check('si-si_FONIPA.txt', GRAPHEMES, PHONEMES)
regtest('si-si_FONIPA', GRAPHEMES, PHONEMES)
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Tavt:]]')
PHONEMES = makePhonemeSet("""
p pʰ b t tʰ d k kʰ ɡ ʔ
m n ɲ ŋ
f v s h x
w j l
t͡ɕ t͡ɕʷ t͡ɕʰ t͡ɕʰʷ
pʷ pʰʷ tʷ dʷ kʰʷ kʷ ɡʷ
mʷ nʷ ɲʷ ŋʷ
fʷ sʷ hʷ xʷ
i ɨ u
ɛ e ə ɔ o
a aː
iə̯ ɨə̯ uə̯
ai̯
˨ ˧˥ ˨˩ ˥ ˦ ˧˩
""")
check('blt-fonipa-t-blt', GRAPHEMES, PHONEMES)
regtest('blt-fonipa-t-blt', GRAPHEMES, PHONEMES)
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import codecs
import icu
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Latn:]]')
PHONEMES = makePhonemeSet("""
m n ɲ
p b t d c ɟ k g
f v s z ʃ ʒ h
t͡ʃ t͡s
r l j ʎ
w
i u e ʊ ɛ ɔ a
ɪa̯ ɪa̯ʊ̯ ɪʊ̯ ɪɛ̯ u ʊa̯ ʊa̯ʊ̯ ʊɛ̯ ʊɛ̯ɪ̯ ʊɔ̯
ɛɪ̯ ɛʊ̯ aɪ̯ aʊ̯
""")
check('rm_SURSILV-rm_FONIPA_SURSILV.txt', GRAPHEMES, PHONEMES)
regtest('rm_SURSILV-rm_FONIPA_SURSILV', GRAPHEMES, PHONEMES)
import codecs
import icu
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Latn:] [:P:]]')
PHONEMES = makePhonemeSet("""
m n
p b d t k ɡ
s z ʃ ʒ
t͡s d͡z t͡ʃ d͡ʒ
f x h
r
v l j
i u
e o
a
ui̯
ei̯ eu̯ oi̯
ai̯ au̯
""")
check('eo-fonipa-t-eo', GRAPHEMES, PHONEMES)
regtest('eo-fonipa-t-eo', GRAPHEMES, PHONEMES)
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import codecs
import icu
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Latn:]]')
PHONEMES = makePhonemeSet("""
m n ɲ
p b t d c ɟ k g
f v s z ʃ ʒ h
t͡ʃ t͡s
r l j ʎ
w
i u e ʊ ɛ ɔ a
ɪa̯ ɪa̯ʊ̯ ɪʊ̯ ɪɛ̯ u ʊa̯ ʊa̯ʊ̯ ʊɛ̯ ʊɛ̯ɪ̯ ʊɔ̯
ɛɪ̯ ɛʊ̯ aɪ̯ aʊ̯
""")
check('rm-fonipa-sursilv-t-rm-sursilv', GRAPHEMES, PHONEMES)
regtest('rm-fonipa-sursilv-t-rm-sursilv', GRAPHEMES, PHONEMES)
import codecs
import icu
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Olck:]]')
# TODO: This phoneme set seems a little large.
# Collect a large corpus, and see which ones actually occur.
# TODO: Is /ɽː/ physiologically possible?
PHONEMES = makePhonemeSet("""
m mː n nː ɳ ɳː ɲ ɲː ŋ ŋː
p pʰ pʼ b bʰ t tʰ tʼ d dʰ ʈ ʈʰ ɖ ɖʰ c cʰ cʼ k kʰ kʼ g ʔ
s sː h
d͡ʒ
ɽ r
l lː
w wː w̃ w̃ː
i iː ĩ ĩː u uː ũ ũː
e eː ẽ ẽː ə əː ə̃ ə̃ː o oː õ õː
ɛ ɛː ɛ̃ ɛ̃ː ɔ ɔː ɔ̃ ɔ̃ː
a aː ã ãː
""")
check('sat-sat_FONIPA.txt', GRAPHEMES, PHONEMES)
regtest('sat-sat_FONIPA', GRAPHEMES, PHONEMES)
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Cyrl:]]')
# TODO(sascha): Verify whether /lʲ/ is really phonemic in Kyrgyz;
# is there really a minimal pair with /l/ versus /lʲ/?
#
# TODO(sascha): No gemination for /p b g q z ʃ f v r/? No long /ɯː/?
PHONEMES = makePhonemeSet("""
m mː n nː ŋ
p b t tː d dː k kː ɡ q
t͡s t͡ʃ d͡ʒ
s sː z ʃ
f v j χ ʁ
r l lː lʲ
i iː y yː ɯ u uː
e eː o oː
ø øː
ɑ ɑː
.
""")
check('ky-fonipa-t-ky', GRAPHEMES, PHONEMES)
regtest('ky-fonipa-t-ky', GRAPHEMES, PHONEMES)
import codecs
import icu
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Latn:] [:P:]]')
PHONEMES = makePhonemeSet("""
m n
p b d t k ɡ
s z ʃ ʒ
t͡s d͡z t͡ʃ d͡ʒ
f x h
r
v l j
i u
e o
a
ui̯
ei̯ eu̯ oi̯
ai̯ au̯
""")
check('eo-eo_FONIPA.txt', GRAPHEMES, PHONEMES)
regtest('eo-eo_FONIPA', GRAPHEMES, PHONEMES)
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import codecs
import icu
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Taml:] [:P:]]')
PHONEMES = makePhonemeSet("""
m n ɲ ɳ ŋ
p b tʳ t̪ d̪ ʈ ɖ k ɡ
f s ʂ sʼ ʃ h x
ʋ r ɻ l ɭ j
t͡ʃ d͡ʒ
i iː u uː
e eː o oː
a aː
aɪ̯ aʊ̯
""")
check('ta-fonipa-t-ta', GRAPHEMES, PHONEMES)
regtest('ta-fonipa-t-ta', GRAPHEMES, PHONEMES)
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Cyrl:]]')
# TODO(sascha): Verify whether /lʲ/ is really phonemic in Kyrgyz;
# is there really a minimal pair with /l/ versus /lʲ/?
#
# TODO(sascha): No gemination for /p b g q z ʃ f v r/? No long /ɯː/?
PHONEMES = makePhonemeSet("""
m mː n nː ŋ
p b t tː d dː k kː ɡ q
t͡s t͡ʃ d͡ʒ
s sː z ʃ
f v j χ ʁ
r l lː lʲ
i iː y yː ɯ u uː
e eː o oː
ø øː
ɑ ɑː
.
""")
check('ky-ky_FONIPA.txt', GRAPHEMES, PHONEMES)
regtest('ky-ky_FONIPA', GRAPHEMES, PHONEMES)
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import codecs
import icu
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Ethi:]]')
PHONEMES = makePhonemeSet("""
m n ɲ ŋ
p pʼ b t tʼ d k kʼ ɡ ʔ
f v s sʼ z ʃ ʒ ʕ h
t͡ʃ t͡ʃʼ d͡ʒ
r j l
w
i ɨ u
e ə o
a
.
""")
check('am-am_FONIPA.txt', GRAPHEMES, PHONEMES)
regtest('am-am_FONIPA', GRAPHEMES, PHONEMES)
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern("[[:Olck:]]")
# TODO: This phoneme set seems a little large.
# Collect a large corpus, and see which ones actually occur.
# TODO: Is /ɽː/ physiologically possible?
PHONEMES = makePhonemeSet(
"""
m mː n nː ɳ ɳː ɲ ɲː ŋ ŋː
p pʰ pʼ b bʰ t tʰ tʼ d dʰ ʈ ʈʰ ɖ ɖʰ c cʰ cʼ k kʰ kʼ g ʔ
s sː h
d͡ʒ
ɽ r
l lː
w wː w̃ w̃ː
i iː ĩ ĩː u uː ũ ũː
e eː ẽ ẽː ə əː ə̃ ə̃ː o oː õ õː
ɛ ɛː ɛ̃ ɛ̃ː ɔ ɔː ɔ̃ ɔ̃ː
a aː ã ãː
"""
)
check("sat-sat_FONIPA.txt", GRAPHEMES, PHONEMES)
regtest("sat-sat_FONIPA", GRAPHEMES, PHONEMES)
PHONEMES = makePhonemeSet("""
m̥ m n̥ n ɲ̥ ɲ ŋ̊ ŋ ɴ
p pʰ b t tʰ d t͡ɕ t͡ɕʰ d͡ʑ k kʰ g ʔ
θ s sʰ z ʃ h
w̥ w j
l̥ l
í ì ḭ
ú ù ṵ
ʊ ʊ́ ʊ̀ ʊ̰
ɪ ɪ́ ɪ̀ ɪ̰
e é è ḛ
ó ò o̰
ə
ɛ ɛ́ ɛ̀ ɛ̰
ɔ́ ɔ̀ ɔ̰
æ
a á à a̰
eɪ̯ éɪ̯ èɪ̯ ḛɪ̯
oʊ̯ óʊ̯ òʊ̯ o̰ʊ̯
əʊ̯
aɪ̯ áɪ̯ àɪ̯ a̰ɪ̯
aʊ̯ áʊ̯ àʊ̯ a̰ʊ̯
.
""")
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import codecs
import icu
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Sinh:] [:Cf:]]')
PHONEMES = makePhonemeSet("""
m n ɲ ŋ
p b ᵐb ⁿd ʈ ɖ ⁿɖ k g ᵑg
s ʃ
t͡ʃ d͡ʒ
f h
r
ʋ l j
w
i iː u uː
e eː ə o oː
æː æ a aː
.
""")
check('si-si_FONIPA.txt', GRAPHEMES, PHONEMES)
regtest('si-si_FONIPA', GRAPHEMES, PHONEMES)
# -*- coding: utf-8 -*-
from __future__ import unicode_literals
import codecs
import icu
from cldr_util import makePhonemeSet, match, check, regtest
GRAPHEMES = icu.UnicodeSet()
GRAPHEMES.applyPattern('[[:Arab:] َ ٰ ْ ِ ُ ٓ ّ ٔ ً \u200c \u200d]')
PHONEMES = makePhonemeSet("""
m n
p b t d k ɡ ʔ
f v s z ʃ ʒ ʁ ɢ h χ
t͡ʃ d͡ʒ
l ɾ j w
i u e o æ ɒ
ː
""")
check('fa-fonipa-t-fa', GRAPHEMES, PHONEMES)
regtest('fa-fonipa-t-fa', GRAPHEMES, PHONEMES)